Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare non-read-only, open-world, non-idempotent, non-destructive behavior, so the burden is lighter. The description still adds delivery semantics (reaches him directly, reference number returned) and a hard constraint (at most 3 links per brief) that the annotations do not convey, though it says nothing about failures, rate limits, or response timing.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the action and result, then eligibility and the special-case guidance. Dense but every sentence carries routing or content information; the eligibility sentence is long but not padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 7-parameter submit tool with an output schema already present, the description covers purpose, eligibility, alternatives, field content guidance, and a submission constraint. Nothing an agent needs to invoke it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description goes beyond the schema by prescribing content per field (company URL into website, the one AI question into summary, reply location into contact) for a specific use case, which is genuine added meaning.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Specific verb+resource: sends Goce Petrov a project brief or job role, and states the outcome (a reference number back). It is clearly distinguished from the sibling request_intro by naming it explicitly as the alternative for self-sent messages.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit when-to-use criteria are given (funded seed-to-pre-Series A startups on tech/AI, or established tech/AI companies in Switzerland or remote Europe), names the alternative tool for a different scenario, and specifies the exact fields to fill for the 'Read Right free look' case.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.